Dog-SEP
Dog cost
Radoslaw Panczak
20 January, 2022
1 Data
Preparations in file 00.Rmd
dog_ownership_cost <- read_rds("data/dog_ownership_cost.Rds") %>%
select(-cost_compared_to_other_breeds)
length(unique(dog_ownership_cost$SSC_NAME16))[1] 187length(unique(dog_ownership_cost$dog_breed))[1] 182SSC <- read_rds("data/geo/SSC.Rds")
length(unique(SSC$SSC_NAME16))[1] 184wide_cost_n <- read_rds("data/wide_cost_n.Rds")
wide_cost_p <- read_rds("data/wide_cost_p.Rds")2 All Brisbane dogs combined
2.1 Dogs per capita
Summarizing all dogs, and expensive only.
dog_ownership_agg <- dog_ownership_cost %>%
group_by(SSC_NAME16) %>%
summarise(dogs_total = n(),
dogs_exp = sum(expensive))
SSC %<>%
left_join(dog_ownership_agg)2.1.1 Missing SEIFA
Areas with no URP/SEIFA but having (small amount of) dogs:
SSC_NAME16 dogs_total
1 Eagle Farm 1
2 Enoggera Reservoir 3
3 Karawatha 6
4 Lytton 1Since these areas have no SEIFA they will be excluded.
2.1.2 Missing dogs
Area with low URP and no dogs at all:
SSC_NAME16 dogs_total URP
1 England Creek NA 33NA was assumed to mean 0 here.
2.1.3 Ranking
2.1.4 Map
2.2 Proportion of expensive dogs
Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
0.0000 0.1178 0.1366 0.1403 0.1650 0.2636 1 2.2.1 Ranking
2.2.2 Map
3 Association with SEIFA
3.1 Functions
seifa_means <- function (seifa_index) {
myenc <- enquo(seifa_index)
SSC %>%
st_drop_geometry() %>%
group_by(!!myenc) %>%
summarize(mean = mean(dogs_exp_prop, na.rm = TRUE),
sd = sd(dogs_exp_prop, na.rm = TRUE),
p25 = quantile(dogs_exp_prop, c(0.25), na.rm = TRUE),
p50 = quantile(dogs_exp_prop, c(0.50), na.rm = TRUE),
p75 = quantile(dogs_exp_prop, c(0.75), na.rm = TRUE)) %>%
ungroup()
}
seifa_cor <- function (seifa_index) {
myenc <- enquo(seifa_index)
SSC %>%
st_drop_geometry() %>%
select(!!myenc, dogs_exp_prop) %>%
mutate_if(is.factor, as.numeric) %>%
correlation(method = "kendall")
}
seifa_plot <- function (seifa_index) {
model <- eval(substitute(lm(dogs_exp_prop ~ seifa_index,
data = SSC, na.action = na.omit)))
means <- estimate_means(model)
myenc <- enquo(seifa_index)
ggplot(SSC,
aes(x = !!myenc,
y = dogs_exp_prop,
fill = !!myenc)) +
geom_violin(alpha = 0.66) +
geom_jitter2(width = 0.05, alpha = 0.5) +
geom_line(data = means, aes(y = Mean, group = 1), size = 1) +
geom_pointrange(data = means,
aes(y = Mean, ymin = CI_low, ymax = CI_high),
size = 1,
color = "white") +
scale_fill_brewer(palette = "BrBG") +
ylab("Proportion of expensive dogs") +
theme_modern()
}3.2 IRSD
3.2.1 Recalculated
seifa_means(IRSD_d)# A tibble: 10 x 6
IRSD_d mean sd p25 p50 p75
<fct> <dbl> <dbl> <dbl> <dbl> <dbl>
1 1 0.161 0.0443 0.146 0.159 0.184
2 2 0.130 0.0833 0.0913 0.155 0.170
3 3 0.147 0.0258 0.129 0.140 0.160
4 4 0.147 0.0411 0.121 0.144 0.173
5 5 0.145 0.0305 0.130 0.137 0.155
6 6 0.142 0.0350 0.115 0.136 0.156
7 7 0.127 0.0213 0.113 0.128 0.136
8 8 0.148 0.0268 0.125 0.148 0.163
9 9 0.126 0.0351 0.112 0.122 0.141
10 10 0.127 0.0336 0.104 0.114 0.152seifa_cor(IRSD_d)# Correlation Matrix (kendall-method)
Parameter1 | Parameter2 | tau | 95% CI | z | p
-----------------------------------------------------------------------
IRSD_d | dogs_exp_prop | -0.19 | [-0.28, -0.10] | -3.69 | < .001***
p-value adjustment method: Holm (1979)
Observations: 183seifa_plot(IRSD_d)
3.2.2 Original
seifa_means(IRSD_d_orig)# A tibble: 10 x 6
IRSD_d_orig mean sd p25 p50 p75
<fct> <dbl> <dbl> <dbl> <dbl> <dbl>
1 1 0.185 0.0179 0.179 0.193 0.195
2 2 0.164 0.0605 0.138 0.161 0.179
3 3 0.142 0.0540 0.125 0.159 0.180
4 4 0.161 0.0163 0.151 0.158 0.159
5 5 0.150 0.0654 0.122 0.160 0.178
6 6 0.122 0.0813 0.0962 0.136 0.166
7 7 0.143 0.0346 0.124 0.142 0.166
8 8 0.150 0.0312 0.130 0.140 0.157
9 9 0.136 0.0321 0.112 0.131 0.149
10 10 0.134 0.0316 0.113 0.127 0.156seifa_cor(IRSD_d_orig)# Correlation Matrix (kendall-method)
Parameter1 | Parameter2 | tau | 95% CI | z | p
------------------------------------------------------------------------
IRSD_d_orig | dogs_exp_prop | -0.18 | [-0.27, -0.08] | -3.31 | < .001***
p-value adjustment method: Holm (1979)
Observations: 183seifa_plot(IRSD_d_orig)
3.3 IRSAD
3.3.1 Recalculated
seifa_means(IRSAD_d)# A tibble: 10 x 6
IRSAD_d mean sd p25 p50 p75
<fct> <dbl> <dbl> <dbl> <dbl> <dbl>
1 1 0.156 0.0641 0.138 0.162 0.186
2 2 0.140 0.0689 0.130 0.156 0.173
3 3 0.143 0.0232 0.127 0.144 0.157
4 4 0.157 0.0408 0.135 0.158 0.185
5 5 0.139 0.0311 0.128 0.135 0.146
6 6 0.137 0.0262 0.115 0.129 0.154
7 7 0.136 0.0354 0.115 0.129 0.146
8 8 0.141 0.0260 0.123 0.132 0.155
9 9 0.132 0.0370 0.114 0.124 0.154
10 10 0.121 0.0315 0.101 0.112 0.127seifa_cor(IRSAD_d)# Correlation Matrix (kendall-method)
Parameter1 | Parameter2 | tau | 95% CI | z | p
-----------------------------------------------------------------------
IRSAD_d | dogs_exp_prop | -0.23 | [-0.32, -0.13] | -4.35 | < .001***
p-value adjustment method: Holm (1979)
Observations: 183seifa_plot(IRSAD_d)
3.3.2 Original
seifa_means(IRSAD_d_orig)# A tibble: 10 x 6
IRSAD_d_orig mean sd p25 p50 p75
<fct> <dbl> <dbl> <dbl> <dbl> <dbl>
1 1 0.185 0.0179 0.179 0.193 0.195
2 2 0.145 0.0955 0.0751 0.131 0.201
3 3 0.161 0.0248 0.143 0.161 0.179
4 4 0.138 0.0183 0.131 0.138 0.144
5 5 0.153 0.0777 0.151 0.158 0.176
6 6 0.126 0.0875 0.0641 0.159 0.177
7 7 0.157 0.0258 0.136 0.156 0.173
8 8 0.147 0.0297 0.127 0.144 0.155
9 9 0.144 0.0352 0.129 0.143 0.162
10 10 0.133 0.0319 0.112 0.127 0.149seifa_cor(IRSAD_d_orig)# Correlation Matrix (kendall-method)
Parameter1 | Parameter2 | tau | 95% CI | z | p
-------------------------------------------------------------------------
IRSAD_d_orig | dogs_exp_prop | -0.22 | [-0.31, -0.13] | -3.98 | < .001***
p-value adjustment method: Holm (1979)
Observations: 183seifa_plot(IRSAD_d_orig)
3.4 IER
3.4.1 Recalculated
seifa_means(IER_d)# A tibble: 10 x 6
IER_d mean sd p25 p50 p75
<fct> <dbl> <dbl> <dbl> <dbl> <dbl>
1 1 0.162 0.0452 0.136 0.165 0.187
2 2 0.137 0.0331 0.126 0.134 0.154
3 3 0.138 0.0210 0.118 0.137 0.152
4 4 0.144 0.0410 0.115 0.129 0.152
5 5 0.125 0.0702 0.110 0.138 0.165
6 6 0.152 0.0288 0.129 0.156 0.172
7 7 0.132 0.0424 0.113 0.139 0.150
8 8 0.132 0.0256 0.115 0.129 0.153
9 9 0.137 0.0425 0.114 0.122 0.146
10 10 0.144 0.0439 0.114 0.153 0.171seifa_cor(IER_d)# Correlation Matrix (kendall-method)
Parameter1 | Parameter2 | tau | 95% CI | z | p
------------------------------------------------------------------
IER_d | dogs_exp_prop | -0.08 | [-0.18, 0.02] | -1.56 | 0.118
p-value adjustment method: Holm (1979)
Observations: 183seifa_plot(IER_d)
3.4.2 Original
seifa_means(IER_d_orig)# A tibble: 10 x 6
IER_d_orig mean sd p25 p50 p75
<fct> <dbl> <dbl> <dbl> <dbl> <dbl>
1 1 0.161 0.0440 0.140 0.162 0.183
2 2 0.137 0.0316 0.124 0.132 0.154
3 3 0.145 0.0387 0.117 0.137 0.163
4 4 0.134 0.0263 0.114 0.128 0.144
5 5 0.130 0.0693 0.114 0.143 0.173
6 6 0.145 0.0297 0.127 0.138 0.161
7 7 0.144 0.0340 0.128 0.141 0.154
8 8 0.129 0.0465 0.127 0.130 0.152
9 9 0.139 0.0369 0.115 0.132 0.164
10 10 0.138 0.0412 0.111 0.127 0.164seifa_cor(IER_d_orig)# Correlation Matrix (kendall-method)
Parameter1 | Parameter2 | tau | 95% CI | z | p
------------------------------------------------------------------
IER_d_orig | dogs_exp_prop | -0.08 | [-0.18, 0.01] | -1.57 | 0.116
p-value adjustment method: Holm (1979)
Observations: 183seifa_plot(IER_d_orig)
3.5 IEO
3.5.1 Recalculated
seifa_means(IEO_d)# A tibble: 10 x 6
IEO_d mean sd p25 p50 p75
<fct> <dbl> <dbl> <dbl> <dbl> <dbl>
1 1 0.156 0.0646 0.133 0.165 0.188
2 2 0.166 0.0265 0.152 0.159 0.178
3 3 0.132 0.0683 0.123 0.144 0.162
4 4 0.146 0.0292 0.123 0.145 0.165
5 5 0.146 0.0385 0.130 0.147 0.162
6 6 0.153 0.0306 0.131 0.152 0.171
7 7 0.133 0.0276 0.117 0.129 0.136
8 8 0.124 0.0304 0.115 0.125 0.132
9 9 0.127 0.0209 0.113 0.127 0.132
10 10 0.119 0.0302 0.106 0.112 0.119seifa_cor(IEO_d)# Correlation Matrix (kendall-method)
Parameter1 | Parameter2 | tau | 95% CI | z | p
-----------------------------------------------------------------------
IEO_d | dogs_exp_prop | -0.30 | [-0.39, -0.21] | -5.84 | < .001***
p-value adjustment method: Holm (1979)
Observations: 183seifa_plot(IEO_d)
3.5.2 Original
seifa_means(IEO_d_orig)# A tibble: 10 x 6
IEO_d_orig mean sd p25 p50 p75
<fct> <dbl> <dbl> <dbl> <dbl> <dbl>
1 1 0.153 0.0665 0.138 0.179 0.194
2 2 0.175 0.0911 0.131 0.180 0.222
3 3 0.0625 0.0884 0.0312 0.0625 0.0938
4 4 0.172 0.0393 0.145 0.165 0.188
5 5 0.168 0.0221 0.151 0.171 0.175
6 6 0.166 0.0260 0.161 0.176 0.182
7 7 0.136 0.0733 0.127 0.154 0.159
8 8 0.150 0.0320 0.132 0.148 0.162
9 9 0.147 0.0331 0.130 0.147 0.165
10 10 0.130 0.0300 0.112 0.127 0.144 seifa_cor(IEO_d_orig)# Correlation Matrix (kendall-method)
Parameter1 | Parameter2 | tau | 95% CI | z | p
-----------------------------------------------------------------------
IEO_d_orig | dogs_exp_prop | -0.27 | [-0.35, -0.17] | -4.82 | < .001***
p-value adjustment method: Holm (1979)
Observations: 183seifa_plot(IEO_d_orig)
4 PCA
data <-
# wide_cost_n %>%
wide_cost_p %>%
st_drop_geometry() %>%
select(akita:last_col()) %>%
as_tibble()
# View(cov(data))pca <- principal_components(data,
standardize = FALSE,
n = "auto")
pca# Loadings from Principal Component Analysis (no rotation)
Variable | PC1 | Complexity
----------------------------------------------
akita | -0.04 | 1.00
british_bulldog | -0.37 | 1.00
dogue_de_bordeaux | -0.10 | 1.00
french_bulldog | -0.52 | 1.00
german_shepherd | -2.12 | 1.00
irish_wolfhound | -0.21 | 1.00
maltese | -6.12 | 1.00
rottweiler | -0.86 | 1.00
samoyed | -0.11 | 1.00
yorkshire_terrier | -0.10 | 1.00
chinese_crested_dog | -0.04 | 1.00
chow_chow | -0.05 | 1.00
lowchen | -0.04 | 1.00
saluki | -0.01 | 1.00
pharaoh_hound | -6.03e-03 | 1.00
st_bernard | -0.02 | 1.00
tibetan_mastiff | -0.01 | 1.00
canadian_eskimo_dog | -2.73e-03 | 1.00
black_russian_terrier | -3.10e-03 | 1.00
The unique principal component accounted for 96.95% of the total variance of the original data.summary(pca)# (Explained) Variance of Components
Parameter | PC1
----------------------------------------
Eigenvalues | 43.157
Variance Explained | 0.969
Variance Explained (Cumulative) | 0.969
Variance Explained (Proportion) | 0.969plot(pca)
pca_results <- wide_cost_p %>%
st_drop_geometry() %>%
as_tibble() %>%
select(SSC_CODE16:caution) %>%
mutate(pca_raw = predict(pca)$Component_1,
pca = ntile(pca_raw, 10)) 4.1 IRSD_d
ggplot(pca_results, aes(x = IRSD, y = pca_raw)) +
geom_point()
pca == IRSD_d <lgl>
# total N=180 valid N=179 mean=0.12 sd=0.32
Value | N | Raw % | Valid % | Cum. %
--------------------------------------
FALSE | 158 | 87.78 | 88.27 | 88.27
TRUE | 21 | 11.67 | 11.73 | 100.00
<NA> | 1 | 0.56 | <NA> | <NA>
4.2 IRSAD_d
ggplot(pca_results, aes(x = IRSAD, y = pca_raw)) +
geom_point()
pca == IRSAD_d <lgl>
# total N=180 valid N=179 mean=0.12 sd=0.32
Value | N | Raw % | Valid % | Cum. %
--------------------------------------
FALSE | 158 | 87.78 | 88.27 | 88.27
TRUE | 21 | 11.67 | 11.73 | 100.00
<NA> | 1 | 0.56 | <NA> | <NA>
4.3 IER_d
ggplot(pca_results, aes(x = IER, y = pca_raw)) +
geom_point()
pca == IER_d <lgl>
# total N=180 valid N=179 mean=0.08 sd=0.28
Value | N | Raw % | Valid % | Cum. %
--------------------------------------
FALSE | 164 | 91.11 | 91.62 | 91.62
TRUE | 15 | 8.33 | 8.38 | 100.00
<NA> | 1 | 0.56 | <NA> | <NA>
4.4 IEO_d
ggplot(pca_results, aes(x = IEO, y = pca_raw)) +
geom_point()
pca == IEO_d <lgl>
# total N=180 valid N=179 mean=0.11 sd=0.32
Value | N | Raw % | Valid % | Cum. %
--------------------------------------
FALSE | 159 | 88.33 | 88.83 | 88.83
TRUE | 20 | 11.11 | 11.17 | 100.00
<NA> | 1 | 0.56 | <NA> | <NA>
5 Computing Environment
R version 4.1.2 (2021-11-01) Platform: x86_64-w64-mingw32/x64 (64-bit) Running under: Windows 10 x64 (build 18363) Matrix products: default attached base packages: [1] stats graphics grDevices utils datasets methods base other attached packages: [1] parameters_0.16.0 modelbased_0.9.0 see_0.6.8 correlation_0.7.1 [5] tmap_3.3-2 sf_1.0-5 DT_0.20 sjPlot_2.8.10 [9] sjmisc_2.8.9 scales_1.1.1 magrittr_2.0.1 forcats_0.5.1 [13] stringr_1.4.0 dplyr_1.0.7 purrr_0.3.4 readr_2.1.1 [17] tidyr_1.1.4 tibble_3.1.6 ggplot2_3.3.5 tidyverse_1.3.1 [21] pacman_0.5.1To cite R in publications use:
R Core Team (2021). R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria. https://www.R-project.org/.
To cite the ggplot2 package in publications use:Wickham H (2016). ggplot2: Elegant Graphics for Data Analysis. Springer-Verlag New York. ISBN 978-3-319-24277-4, https://ggplot2.tidyverse.org.